© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36367
    Prev
    Next
    INDEX
    Explanations

    subset of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     være
    0.80
     it
    0.74
    ット
    0.71
     być
    0.70
    </strong>
    0.70
     have
    0.69
    ін
    0.69
    لی
    0.66
     è
    0.66
     mów
    0.65
    POSITIVE LOGITS
    x
    0.81
    在
    0.66
    nich
    0.64
    slaught
    0.63
    cies
    0.61
    nfasis
    0.60
    yse
    0.59
    AI
    0.59
    CloseOperation
    0.59
    Adopt
    0.59
    Activations Density 0.002%

    No Known Activations